Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ----
    -0.07
    _Level
    -0.07
     Serve
    -0.07
    Diese
    -0.06
    Streaming
    -0.06
    _DIRECT
    -0.06
    开源
    -0.06
      ↵
    -0.06
    /The
    -0.06
     SECRET
    -0.06
    POSITIVE LOGITS
    ,url
    0.07
    .startTime
    0.07
    DrawerToggle
    0.07
     produção
    0.07
     выполня
    0.07
    馄
    0.07
    (propertyName
    0.07
    萚
    0.07
     yanında
    0.06
     الحقوق
    0.06
    Act Density 0.126%

    No Known Activations